Paper: Unsupervised Induction of Contingent Event Pairs from Film Scenes

ACL ID D13-1036
Title Unsupervised Induction of Contingent Event Pairs from Film Scenes
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

Human engagement in narrative is partially driven by reasoning about discourse relations between narrative events, and the expectations about what is likely to happen next that results from such reasoning. Researchers in NLP have tackled modeling such expectations from a range of perspectives, including treating it as the inference of the CONTINGENT discourse relation, or as a type of common-sense causal reasoning. Our approach is to model likeli- hood between events by drawing on several of these lines of previous work. We implement and evaluate different unsupervised methods for learning event pairs that are likely to be CONTINGENT on one another. We refine event pairs that we learn from a corpus of film scene descriptions utilizing web search counts, and evaluate our results by collecti...